Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4364 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0000

Data Index: 150161 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0215. Min Act: -0.0000

Data Index: 455772 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0210. Min Act: -0.0000

Data Index: 845492 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0188. Min Act: -0.0000

Data Index: 445680 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0188. Min Act: -0.0000

Data Index: 63250 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0181. Min Act: -0.0000

Data Index: 1110042 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0182. Min Act: -0.0000

Data Index: 606213 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0178. Min Act: -0.0000

Data Index: 716625 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0160. Min Act: -0.0000

Data Index: 666858 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0143. Min Act: -0.0000

Data Index: 1358749 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0164. Min Act: -0.0000

Data Index: 301722 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0161. Min Act: -0.0000

Data Index: 886033 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0159. Min Act: -0.0000

Data Index: 959469 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0152. Min Act: -0.0000

Data Index: 345128 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0155. Min Act: -0.0000

Data Index: 774907 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0143. Min Act: -0.0000

Data Index: 616175 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0166. Min Act: -0.0000

Data Index: 360554 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0137. Min Act: -0.0000

Data Index: 626453 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0143. Min Act: -0.0000

Data Index: 942998 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0168. Min Act: -0.0000

Data Index: 665067 (C4 (Web Text))

Max Activating Token Index: 850